[PATCH 05/27] [AARCH64] Use PTR_REG in crti.S.

From: Yury Norov
Date: Tue Jun 21 2016 - 01:11:10 EST

From: Andrew Pinski <apinski@xxxxxxxxxx>

call_weak_fn loads from a pointer, so use PTR_REG so the load
is 32bits for ILP32.

* sysdeps/aarch64/crti.S: Include sysdep.h
(call_weak_fn): Use PTR_REG when loading from
PREINIT_FUNCTION.

AARCH64: Make RTLD_START paramatizable

Make RTLD_START paramatizable for ILP32 and LP64 usage and provides common
code between ILP32.

* sysdeps/aarch64/dl-machine.h (RTLD_START): Rename to ...
(RTLD_START_1): This and add PTR, PTR_SIZE_LOG, and PTR_SP arguments.
(RTLD_START): New macro which uses RTLD_START_1.

Signed-off-by: Yury Norov <ynorov@xxxxxxxxxxxxxxxxxx>
---
sysdeps/aarch64/crti.S | 3 +-
sysdeps/aarch64/dl-machine.h | 128 ++++++++++++++++++++++---------------------
2 files changed, 69 insertions(+), 62 deletions(-)

diff --git a/sysdeps/aarch64/crti.S b/sysdeps/aarch64/crti.S
index 53ccb42..6e149b5 100644
--- a/sysdeps/aarch64/crti.S
+++ b/sysdeps/aarch64/crti.S
@@ -39,6 +39,7 @@
they can be called as functions. The symbols _init and _fini are
magic and cause the linker to emit DT_INIT and DT_FINI. */

+#include <sysdep.h>
#include <libc-symbols.h>

#ifndef PREINIT_FUNCTION
@@ -60,7 +61,7 @@
.type call_weak_fn, %function
call_weak_fn:
adrp x0, :got:PREINIT_FUNCTION
- ldr x0, [x0, #:got_lo12:PREINIT_FUNCTION]
+ ldr PTR_REG(0), [x0, #:got_lo12:PREINIT_FUNCTION]
cbz x0, 1f
b PREINIT_FUNCTION
1:
diff --git a/sysdeps/aarch64/dl-machine.h b/sysdeps/aarch64/dl-machine.h
index a16cb11..7a49852 100644
--- a/sysdeps/aarch64/dl-machine.h
+++ b/sysdeps/aarch64/dl-machine.h
@@ -126,68 +126,74 @@ elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
/* Initial entry point for the dynamic linker. The C function
_dl_start is the real entry point, its return value is the user
program's entry point */
+#ifdef __LP64__
+#define RTLD_START RTLD_START_1("x", "3", "sp")
+#else
+#define RTLD_START RTLD_START_1("w", "2", "wsp")
+#endif
+

-#define RTLD_START asm ("\
-.text \n\
-.globl _start \n\
-.type _start, %function \n\
-.globl _dl_start_user \n\
-.type _dl_start_user, %function \n\
-_start: \n\
- mov x0, sp \n\
- bl _dl_start \n\
- // returns user entry point in x0 \n\
- mov x21, x0 \n\
-_dl_start_user: \n\
- // get the original arg count \n\
- ldr x1, [sp] \n\
- // get the argv address \n\
- add x2, sp, #8 \n\
- // get _dl_skip_args to see if we were \n\
- // invoked as an executable \n\
- adrp x4, _dl_skip_args \n\
- ldr w4, [x4, #:lo12:_dl_skip_args] \n\
- // do we need to adjust argc/argv \n\
- cmp w4, 0 \n\
- beq .L_done_stack_adjust \n\
- // subtract _dl_skip_args from original arg count \n\
- sub x1, x1, x4 \n\
- // store adjusted argc back to stack \n\
- str x1, [sp] \n\
- // find the first unskipped argument \n\
- mov x3, x2 \n\
- add x4, x2, x4, lsl #3 \n\
- // shuffle argv down \n\
-1: ldr x5, [x4], #8 \n\
- str x5, [x3], #8 \n\
- cmp x5, #0 \n\
- bne 1b \n\
- // shuffle envp down \n\
-1: ldr x5, [x4], #8 \n\
- str x5, [x3], #8 \n\
- cmp x5, #0 \n\
- bne 1b \n\
- // shuffle auxv down \n\
-1: ldp x0, x5, [x4, #16]! \n\
- stp x0, x5, [x3], #16 \n\
- cmp x0, #0 \n\
- bne 1b \n\
- // Update _dl_argv \n\
- adrp x3, _dl_argv \n\
- str x2, [x3, #:lo12:_dl_argv] \n\
-.L_done_stack_adjust: \n\
- // compute envp \n\
- add x3, x2, x1, lsl #3 \n\
- add x3, x3, #8 \n\
- adrp x16, _rtld_local \n\
- add x16, x16, #:lo12:_rtld_local \n\
- ldr x0, [x16] \n\
- bl _dl_init \n\
- // load the finalizer function \n\
- adrp x0, _dl_fini \n\
- add x0, x0, #:lo12:_dl_fini \n\
- // jump to the user_s entry point \n\
- br x21 \n\
+#define RTLD_START_1(PTR, PTR_SIZE_LOG, PTR_SP) asm ("\
+.text \n\
+.globl _start \n\
+.type _start, %function \n\
+.globl _dl_start_user \n\
+.type _dl_start_user, %function \n\
+_start: \n\
+ mov " PTR "0, " PTR_SP " \n\
+ bl _dl_start \n\
+ // returns user entry point in x0 \n\
+ mov x21, x0 \n\
+_dl_start_user: \n\
+ // get the original arg count \n\
+ ldr " PTR "1, [sp] \n\
+ // get the argv address \n\
+ add " PTR "2, " PTR_SP ", #(1<<" PTR_SIZE_LOG ") \n\
+ // get _dl_skip_args to see if we were \n\
+ // invoked as an executable \n\
+ adrp x4, _dl_skip_args \n\
+ ldr w4, [x4, #:lo12:_dl_skip_args] \n\
+ // do we need to adjust argc/argv \n\
+ cmp w4, 0 \n\
+ beq .L_done_stack_adjust \n\
+ // subtract _dl_skip_args from original arg count \n\
+ sub " PTR "1, " PTR "1, " PTR "4 \n\
+ // store adjusted argc back to stack \n\
+ str " PTR "1, [sp] \n\
+ // find the first unskipped argument \n\
+ mov " PTR "3, " PTR "2 \n\
+ add " PTR "4, " PTR "2, " PTR "4, lsl #" PTR_SIZE_LOG " \n\
+ // shuffle argv down \n\
+1: ldr " PTR "5, [x4], #(1<<" PTR_SIZE_LOG ") \n\
+ str " PTR "5, [x3], #(1<<" PTR_SIZE_LOG ") \n\
+ cmp " PTR "5, #0 \n\
+ bne 1b \n\
+ // shuffle envp down \n\
+1: ldr " PTR "5, [x4], #(1<<" PTR_SIZE_LOG ") \n\
+ str " PTR "5, [x3], #(1<<" PTR_SIZE_LOG ") \n\
+ cmp " PTR "5, #0 \n\
+ bne 1b \n\
+ // shuffle auxv down \n\
+1: ldp " PTR "0, " PTR "5, [x4, #(2<<" PTR_SIZE_LOG ")]! \n\
+ stp " PTR "0, " PTR "5, [x3], #(2<<" PTR_SIZE_LOG ") \n\
+ cmp " PTR "0, #0 \n\
+ bne 1b \n\
+ // Update _dl_argv \n\
+ adrp x3, _dl_argv \n\
+ str " PTR "2, [x3, #:lo12:_dl_argv] \n\
+.L_done_stack_adjust: \n\
+ // compute envp \n\
+ add " PTR "3, " PTR "2, " PTR "1, lsl #" PTR_SIZE_LOG " \n\
+ add " PTR "3, " PTR "3, #(1<<" PTR_SIZE_LOG ") \n\
+ adrp x16, _rtld_local \n\
+ add " PTR "16, " PTR "16, #:lo12:_rtld_local \n\
+ ldr " PTR "0, [x16] \n\
+ bl _dl_init \n\
+ // load the finalizer function \n\
+ adrp x0, _dl_fini \n\
+ add " PTR "0, " PTR "0, #:lo12:_dl_fini \n\
+ // jump to the user_s entry point \n\
+ br x21 \n\
");

#define elf_machine_type_class(type) \
--
2.7.4